CN114429552A - Object attribute identification method and device, readable storage medium and electronic equipment - Google Patents
Object attribute identification method and device, readable storage medium and electronic equipment Download PDFInfo
- Publication number
- CN114429552A CN114429552A CN202210074401.6A CN202210074401A CN114429552A CN 114429552 A CN114429552 A CN 114429552A CN 202210074401 A CN202210074401 A CN 202210074401A CN 114429552 A CN114429552 A CN 114429552A
- Authority
- CN
- China
- Prior art keywords
- target
- sequence
- module
- feature sequence
- attribute
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The disclosure relates to an object attribute identification method, an object attribute identification device, a readable storage medium and an electronic device. The method comprises the following steps: acquiring a target image, wherein the target image comprises a target object and object description information of the target object; extracting a key information characteristic sequence of a target object and a multi-modal characteristic sequence corresponding to a target attribute of the target object from a target image, wherein the multi-modal characteristic sequence comprises a visual characteristic sequence and a semantic characteristic sequence of the target attribute; and determining a plurality of object attributes of the target object according to the key information characteristic sequence and the multi-modal characteristic sequence. Therefore, when the attribute of the target object in the target image is identified, the key information characteristics of the target object are referred, and the visual characteristics and the semantic characteristics of the target attribute are referred, so that the characteristic dimensionality of the target object is richer, the information is more comprehensive, and the accuracy of the identification of the object attribute and the richness of the object attribute are improved.
Description
Technical Field
The present disclosure relates to the field of image processing technologies, and in particular, to an object attribute identification method, an object attribute identification device, a readable storage medium, and an electronic device.
Background
In recent years, with the rapid development of information technology, image structuring has become a standard in image understanding. The image structuring is a technology for extracting key target objects (such as vehicles, pedestrians and the like) based on image content information, and organizes the image content into structured information which can be understood by computers and human beings according to semantic relations by adopting processing means such as space-time segmentation, feature extraction, object identification and the like. The identification of the attributes of the object in the image is an important functional module for image structuring, which can predict various attribute labels of the object from the image, such as the age, sex, and clothing style of the pedestrian, the license plate number, age, etc. of the vehicle, and can be used for intelligent application of image perception world. How to improve the accuracy and richness of object attribute identification of an image becomes a key for enhancing image understanding.
Disclosure of Invention
This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
In a first aspect, the present disclosure provides an object attribute identification method, including:
acquiring a target image, wherein the target image comprises a target object and object description information of the target object;
extracting a key information feature sequence of the target object and a multi-modal feature sequence corresponding to a target attribute of the target object from the target image, wherein the multi-modal feature sequence comprises a visual feature sequence and a semantic feature sequence of the target attribute;
determining a plurality of object attributes of the target object according to the key information feature sequence and the multi-modal feature sequence, wherein the plurality of object attributes include the target attribute.
In a second aspect, the present disclosure provides an object attribute identification apparatus, including:
the device comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring a target image, and the target image comprises a target object and object description information of the target object;
the first extraction module is used for extracting a key information feature sequence of the target object and a multi-modal feature sequence corresponding to a target attribute of the target object from the target image acquired by the acquisition module, wherein the multi-modal feature sequence comprises a visual feature sequence and a semantic feature sequence of the target attribute;
a determining module, configured to determine a plurality of object attributes of the target object according to the key information feature sequence and the multi-modal feature sequence extracted by the first extracting module, where the plurality of object attributes include the target attribute.
In a third aspect, the present disclosure provides a computer readable medium having stored thereon a computer program which, when executed by a processing apparatus, performs the steps of the method provided by the first aspect of the present disclosure.
In a fourth aspect, the present disclosure provides an electronic device comprising:
a storage device having a computer program stored thereon;
processing means for executing the computer program in the storage means to implement the steps of the method provided by the first aspect of the present disclosure.
In the technical scheme, firstly, a target image is obtained, wherein the target image comprises a target object and object description information of the target object; secondly, extracting a key information characteristic sequence of the target object and a multi-modal characteristic sequence corresponding to the target attribute of the target object from the target image, wherein the multi-modal characteristic sequence comprises a visual characteristic sequence and a semantic characteristic sequence of the target attribute; and finally, determining a plurality of object attributes of the target object according to the key information characteristic sequence and the multi-modal characteristic sequence. Therefore, when the attribute of the target object in the target image is identified, the key information characteristics of the target object are referred, and the visual characteristics and the semantic characteristics of the target attribute are referred, so that the characteristic dimensionality of the target object is richer, the information is more comprehensive, and the accuracy of the identification of the object attribute and the richness of the object attribute are improved.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows.
Drawings
The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and features are not necessarily drawn to scale. In the drawings:
FIG. 1 is a flow diagram illustrating a method for object property identification in accordance with an exemplary embodiment.
FIG. 2 is a schematic diagram illustrating the structure of a multi-modal feature extraction model, according to an example embodiment.
FIG. 3 is a schematic diagram illustrating the structure of a multimodal fusion model, according to an exemplary embodiment.
Fig. 4 is a flowchart illustrating an object attribute identification method according to another exemplary embodiment.
Fig. 5 is a schematic diagram illustrating an appearance feature extraction model according to an exemplary embodiment.
Fig. 6 is a flowchart illustrating an object attribute identification method according to another exemplary embodiment.
FIG. 7 is a block diagram illustrating a global visual feature extraction model in accordance with an exemplary embodiment.
Fig. 8 is a block diagram illustrating an object attribute identification apparatus according to an example embodiment.
FIG. 9 is a block diagram illustrating an electronic device in accordance with an example embodiment.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.
It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order, and/or performed in parallel. Moreover, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.
The term "include" and variations thereof as used herein are open-ended, i.e., "including but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the following description.
It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.
It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.
The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.
FIG. 1 is a flow diagram illustrating a method for object property identification in accordance with an exemplary embodiment. As shown in fig. 1, the method may include the following S101 to S103.
In S101, a target image is acquired.
The target image includes a target object (specifically, an image of the target object) and object description information of the target object, where the target object may be, for example, a vehicle, a pedestrian, a bookcase, a television, and the object description information is text for describing the target object.
In S102, a key information feature sequence of the target object and a multi-modal feature sequence corresponding to the target attribute of the target object are extracted from the target image.
In the present disclosure, the multi-modal feature sequence includes a visual feature sequence and a semantic feature sequence of the target attribute, wherein the target attribute may be any attribute of a target object that is of great interest to the user, for example, the target object is a person, and the target attribute is an age.
In S103, a plurality of object attributes of the target object are determined based on the key information feature sequence and the multimodal feature sequence.
In the present disclosure, the plurality of object attributes includes the above-described target attribute.
Illustratively, the target object is a pedestrian, and the plurality of object attributes may include age, height, gender, style of clothing, hair style, and the like.
Further illustratively, the target object is an item (e.g., bookcase, vehicle), and the plurality of object attributes may include a category, a brand, a name, basic parameters, a volume, a range of use, and the like.
In the technical scheme, firstly, a target image is obtained, wherein the target image comprises a target object and object description information of the target object; secondly, extracting a key information characteristic sequence of the target object and a multi-modal characteristic sequence corresponding to the target attribute of the target object from the target image, wherein the multi-modal characteristic sequence comprises a visual characteristic sequence and a semantic characteristic sequence of the target attribute; and finally, determining a plurality of object attributes of the target object according to the key information characteristic sequence and the multi-modal characteristic sequence. Therefore, when the attribute of the target object in the target image is identified, the key information characteristics of the target object are referred, and the visual characteristics and the semantic characteristics of the target attribute are referred, so that the characteristic dimensionality of the target object is richer, the information is more comprehensive, and the accuracy of the identification of the object attribute and the richness of the object attribute are improved.
A detailed description will be given below of a specific embodiment of extracting the key information feature sequence of the target object from the target image in S102. Specifically, the method can be realized by the following steps (1) and (2):
(1) and performing text recognition on the target image to obtain a recognition text.
In the present disclosure, the identification text may be a multilingual text or a single-language text, and the present disclosure is not particularly limited.
In addition, the target image may be input into a pre-trained text recognition model to obtain a recognized text, where the text recognition model may be, for example, a convolutional recurrent neural network, an attention-based codec network, or the like.
(2) And inputting the recognition text into a pre-trained multi-language model to obtain a key information characteristic sequence of the target object.
In the present disclosure, the multilingual language model is used to extract object key features in the recognition text corresponding to the target image. Illustratively, the multilingual language model may be composed of a plurality (e.g., 12) of sequentially-concatenated coding networks and a plurality (e.g., 6) of sequentially-concatenated decoding networks, wherein a last coding network of the plurality of sequentially-concatenated coding networks is concatenated with a first decoding network of the plurality of sequentially-concatenated decoding networks.
The embodiments of the present disclosure are not limited to the above coding network, and may be implemented by using any existing or future coding network (e.g., an Encoder module in a transform model, an Encoder module in a former model, etc.).
The embodiments of the present disclosure are not limited to the above decoding network, and may be implemented by using any existing or future decoding network (e.g., Decoder module in transform model, Decoder module in former model, etc.).
A detailed description will be given below of a specific embodiment of extracting a multimodal feature sequence corresponding to a target attribute of a target object from a target image in S102. Specifically, the target image may be input to a pre-trained multi-modal feature extraction model to obtain a multi-modal feature sequence corresponding to the target attribute of the target object.
As shown in fig. 2, the multi-modal feature extraction model may include: the system comprises a first target detection module, a first preprocessing module, a first full-connection module, a text recognition module, a multilingual language submodel, a splicing module, a first coding module and a second full-connection module.
The first target detection module is used for extracting a first area where a target attribute identifier of a target object is located from a target image, wherein the identifier may be, for example, a license plate number, a brand logo, and the like; a first preprocessing module, connected to the first target detection module, for normalizing the first region into an image of a first preset size (e.g., 32 × 32), and straightening the normalized image into a one-dimensional row vector of a first preset length (e.g., 1024); the first full-connection module is connected with the first preprocessing module and used for generating a visual feature sequence of the target attribute according to the one-dimensional row vector with the first preset length; the text recognition module is connected with the first target detection module and used for performing text recognition on the first area to obtain an attribute description text of the target attribute, such as a brand word; the multilingual language submodel is connected with the text recognition module and used for extracting a semantic feature sequence of the target attribute from the attribute description text; the splicing module is respectively connected with the first full-connection module and the multilingual language submodel and is used for splicing the visual characteristic sequence and the semantic characteristic sequence of the target attribute to obtain a spliced sequence; the first coding module is connected with the splicing module and used for coding the splicing sequence to obtain a first coding sequence; and the second full-connection module is connected with the first coding module and used for performing dimensionality reduction processing on the first coding sequence to obtain a multi-modal characteristic sequence with preset dimensionality corresponding to the target attribute.
In the present disclosure, the first target detection module may be, for example, a yolo (young Only Look once) network, a Single-stage multi-box Detector (SSD), or the like. The text recognition module can be, for example, a convolutional recurrent neural network, an attention-based codec network, or the like. The structure of the multilingual language submodel may be the same as the multilingual language submodel described above.
For example, the first fully-connected module may include 2 fully-connected layers connected in series, the second fully-connected module may include 2 fully-connected layers, and the first encoding module may include 4 encoding networks connected in series, where the embodiment of the present disclosure does not limit the above 4 encoding networks connected in series, and may be implemented by using any existing or future encoding network (e.g., an Encoder module in a transform model, etc.).
In addition, the lengths of the visual characteristic sequence and the semantic characteristic sequence of the target attribute are preset dimensions, and the dimension of the splicing sequence is 2 times of the preset dimension. Illustratively, the preset dimension is 128 dimensions.
A specific embodiment of determining a plurality of object attributes of the target object from the key information feature sequence and the multi-modal feature sequence in S103 will be described in detail below. Specifically, the key information feature sequence and the multi-modal feature sequence may be input into a pre-trained multi-modal fusion model to obtain a plurality of object attributes of the target object.
As shown in fig. 3, the multi-modal fusion model may include a second encoding module, and a plurality of first decoding modules (N decoding modules are illustrated in fig. 3, N is greater than 1) corresponding to the attribute categories of the plurality of object attributes, and each of the first decoding modules is connected to the second encoding module.
The second coding module is used for coding a first characteristic matrix formed by the key information characteristic sequence and the multi-modal characteristic sequence to obtain a second coding sequence, wherein the dimensionalities of the key information characteristic sequence and the multi-modal characteristic sequence are preset dimensionalities;
and the first decoding module is used for generating the object attributes under the corresponding attribute categories according to the second coding sequence, wherein the attribute categories of each object attribute are different, namely the number of the first decoding modules is equal to the number of the object attributes.
As shown in fig. 3, the first decoding module 1 and the attribute class object of the object attribute a1 are used to generate the object attribute a1, the first decoding module 2 and the attribute class object of the object attribute a2 are used to generate the object attributes a2 and … …, and the first decoding module N and the attribute class object of the object attribute aN are used to generate the object attribute aN.
Illustratively, the second encoding module may include 12 encoding networks connected in series, and the first decoding module may include a decoding network.
In order to further improve the accuracy of object attribute identification and the richness of object attributes, when the object attribute identification is performed, in addition to the key information feature sequence and the multi-modal feature sequence, the appearance features of the target object can be referred to. Specifically, as shown in fig. 4, the method may further include the following S104.
In S104, a sequence of appearance features of the target object is extracted from the target image.
In this case, in S103, a plurality of object attributes of the target object may be specified from the key information feature sequence, the multi-modal feature sequence, and the appearance feature sequence. Specifically, the key information feature sequence, the multi-modal feature sequence, and the appearance feature sequence may be input to a pre-trained multi-modal fusion model, and a plurality of object attributes of the target object may be obtained, where the second encoding module in the multi-modal fusion model is configured to encode a feature matrix formed by the key information feature sequence, the multi-modal feature sequence, and the appearance feature sequence.
A specific embodiment of extracting the appearance feature sequence of the target object from the target image in S104 is described in detail below. Specifically, the target image may be input into a pre-trained appearance feature extraction model to obtain an appearance feature sequence of the target object.
As shown in fig. 5, the appearance feature extraction model may include a second target detection module, a second preprocessing module, a third coding module, and a third full-connection module, which are connected in sequence.
The second target detection module is used for extracting a second area where the appearance of the target object is located from the target image, wherein the appearance can comprise the appearance of the target object, the package of the target object and the like; a second preprocessing module, configured to normalize the second region to an image of a second preset size (e.g., 16 × 16), and straighten the normalized image to a one-dimensional row vector of a second preset length (e.g., 256); the third coding module is used for coding the one-dimensional row vector with the second preset length to obtain a third coding sequence; and the third full-connection module is used for performing dimensionality reduction processing on the third coding sequence to obtain an appearance characteristic sequence of the target object with preset dimensionality.
In the present disclosure, the second target detection module may be, for example, a YOLO network, an SSD, or the like.
For example, the third encoding module may include a 2-layer tandem encoding network, where the embodiment of the present disclosure does not limit the above 2-layer tandem encoding network, and may be implemented by using any existing or future encoding network (e.g., an Encoder module in a transform model, an Encoder module in a transformer model, etc.); the third fully-connected module may include 2 fully-connected layers in series.
In order to further improve the accuracy of object attribute identification and the richness of object attributes, when the object attribute identification is performed, in addition to the key information feature sequence, the multi-modal feature sequence and the appearance features of the target object, a global visual feature sequence of the target image can be referred to. Specifically, as shown in fig. 6, the above method may further include the following S105.
In S105, a global visual feature sequence of the target image is extracted from the target image.
In this case, in S103, a plurality of object attributes of the target object may be determined based on the key information feature sequence, the multi-modal feature sequence, the appearance feature sequence, and the global visual feature sequence. Specifically, the key information feature sequence, the multi-modal feature sequence, the appearance feature sequence, and the global visual feature sequence may be input into a pre-trained multi-modal fusion model to obtain a plurality of object attributes of the target object, wherein the second encoding module in the multi-modal fusion model is configured to encode a feature matrix formed by the key information feature sequence, the multi-modal feature sequence, the appearance feature sequence, and the global visual feature sequence.
In addition, the lengths of the key information feature sequence, the multi-modal feature sequence, the appearance feature sequence and the global visual feature sequence are all preset lengths.
A detailed description will be given below of a specific embodiment of extracting the global visual feature sequence of the target object from the target image in S105. Specifically, the target image may be input into a pre-trained global visual feature extraction model to obtain a global visual feature sequence of the target image.
As shown in fig. 7, the global visual feature extraction model may include a third preprocessing module, a fourth fully-connected module, a fourth encoding module, and a second decoding module, which are connected in sequence.
The third preprocessing module is configured to adjust the target image to a third preset size (e.g., 256 × 256), divide the target image obtained after the size adjustment into a plurality of image blocks according to a fourth preset size (e.g., 16 × 16), straighten each image block into one-dimensional feature vectors of a third preset length (e.g., 256), and form the one-dimensional feature vectors of each third preset length (e.g., 256) into a second feature matrix; the fourth full-connection module is used for generating an original characteristic sequence corresponding to the target image according to the second characteristic matrix; the fourth coding module is used for coding the original characteristic sequence to obtain a fourth coding sequence; and the second decoding module is used for decoding the fourth coding sequence to obtain a global visual characteristic sequence of the target image.
Illustratively, the fourth fully-connected module may include 2 fully-connected layers in series, the fourth encoding module may include 6 encoding networks in series, and the second decoding module may include a decoding network.
Fig. 8 is a block diagram illustrating an object attribute identification apparatus according to an example embodiment. As shown in fig. 8, the apparatus 800 includes:
an obtaining module 801, configured to obtain a target image, where the target image includes a target object and object description information of the target object;
a first extraction module 802, configured to extract, from the target image acquired by the acquisition module 801, a key information feature sequence of the target object and a multi-modal feature sequence corresponding to a target attribute of the target object, where the multi-modal feature sequence includes a visual feature sequence and a semantic feature sequence of the target attribute;
a determining module 803, configured to determine a plurality of object attributes of the target object according to the key information feature sequence and the multi-modal feature sequence extracted by the first extracting module 802, where the plurality of object attributes include the target attribute.
In the technical scheme, firstly, a target image is obtained, wherein the target image comprises a target object and object description information of the target object; secondly, extracting a key information characteristic sequence of the target object and a multi-modal characteristic sequence corresponding to the target attribute of the target object from the target image, wherein the multi-modal characteristic sequence comprises a visual characteristic sequence and a semantic characteristic sequence of the target attribute; and finally, determining a plurality of object attributes of the target object according to the key information characteristic sequence and the multi-modal characteristic sequence. Therefore, when the attribute of the target object in the target image is identified, the key information characteristics of the target object are referred, and the visual characteristics and the semantic characteristics of the target attribute are referred, so that the characteristic dimensionality of the target object is richer, the information is more comprehensive, and the accuracy of the identification of the object attribute and the richness of the object attribute are improved.
Optionally, the first extraction module 802 is configured to input the target image into a pre-trained multi-modal feature extraction model, so as to obtain a multi-modal feature sequence corresponding to the target attribute of the target object.
Optionally, the multi-modal feature extraction model comprises:
the first target detection module is used for extracting a first area where the identification of the target attribute of the target object is located from the target image;
the first preprocessing module is connected with the first target detection module and used for normalizing the first area into an image with a first preset size and straightening the image obtained after normalization into a one-dimensional row vector with a first preset length;
the first full-connection module is connected with the first preprocessing module and used for generating a visual feature sequence of the target attribute according to the one-dimensional row vector with the first preset length;
the text recognition module is connected with the first target detection module and used for performing text recognition on the first area to obtain an attribute description text of the target attribute;
the multilingual language submodel is connected with the text recognition module and used for extracting a semantic feature sequence of the target attribute from the attribute description text;
the splicing module is respectively connected with the first full-connection module and the multilingual language submodel and is used for splicing the visual characteristic sequence of the target attribute and the semantic characteristic sequence to obtain a spliced sequence;
the first coding module is connected with the splicing module and used for coding the splicing sequence to obtain a first coding sequence;
and the second full-connection module is connected with the first coding module and used for performing dimensionality reduction processing on the first coding sequence to obtain a multi-modal characteristic sequence with preset dimensionality corresponding to the target attribute.
Optionally, the first extraction module 802 includes:
the recognition submodule is used for carrying out text recognition on the target image to obtain a recognition text, wherein the recognition text is a multilingual text or a monolingual text;
and the input submodule is used for inputting the recognition text into a pre-trained multi-language model to obtain a key information characteristic sequence of the target object.
Optionally, the determining module 802 is configured to input the key information feature sequence and the multi-modal feature sequence into a pre-trained multi-modal fusion model to obtain multiple object attributes of the target object;
wherein the multimodal fusion model comprises:
the second coding module is used for coding a first feature matrix formed by the key information feature sequence and the multi-modal feature sequence to obtain a second coding sequence, wherein the dimensionalities of the key information feature sequence and the multi-modal feature sequence are preset dimensionalities;
and the first decoding modules are respectively connected with the second coding module and used for generating the object attributes under the corresponding attribute categories according to the second coding sequence, wherein the attribute categories of the object attributes are different.
Optionally, the apparatus 800 further comprises:
the second extraction module is used for extracting the appearance characteristic sequence of the target object from the target image;
the determining module 803 is configured to determine a plurality of object attributes of the target object according to the key information feature sequence, the multi-modal feature sequence, and the appearance feature sequence.
Optionally, the second extraction module is configured to input the target image into a pre-trained appearance feature extraction model to obtain an appearance feature sequence of the target object, where the appearance feature extraction model includes a second target detection module, a second preprocessing module, a third coding module, and a third full-connection module, which are connected in sequence;
the second target detection module is used for extracting a second area where the appearance of the target object is located from the target image;
the second preprocessing module is used for normalizing the second area into an image with a second preset size and straightening the image obtained after normalization into a one-dimensional row vector with a second preset length;
the third coding module is configured to code the one-dimensional row vector with the second preset length to obtain a third coding sequence;
and the third full-connection module is used for performing dimensionality reduction processing on the third coding sequence to obtain an appearance characteristic sequence of the target object with preset dimensionality.
Optionally, the apparatus 800 further comprises:
the third extraction module is used for extracting a global visual feature sequence of the target image from the target image;
the determining module 803 is configured to determine a plurality of object attributes of the target object according to the key information feature sequence, the multi-modal feature sequence, the appearance feature sequence, and the global visual feature sequence.
Optionally, the third extraction module is configured to input the target image into a pre-trained global visual feature extraction model to obtain a global visual feature sequence of the target image, where the global visual feature extraction model includes a third preprocessing module, a fourth fully-connected module, a fourth encoding module, and a second decoding module, which are connected in sequence;
the third preprocessing module is configured to adjust the target image to a third preset size, divide the target image obtained after the size adjustment into a plurality of image blocks according to a fourth preset size, straighten each image block into one-dimensional eigenvectors of a third preset length, and form a second eigenvector of the third preset length into a second eigenvector matrix;
the fourth full-connection module is configured to generate an original feature sequence corresponding to the target image according to the second feature matrix;
the fourth coding module is used for coding the original characteristic sequence to obtain a fourth coding sequence;
and the second decoding module is used for decoding the fourth coding sequence to obtain a global visual feature sequence of the target image.
The present disclosure also provides a computer readable medium, on which a computer program is stored, which when executed by a processing apparatus implements the steps of the above object property identification method provided by the present disclosure.
Referring now to fig. 9, a schematic diagram of an electronic device (terminal device or server) 600 suitable for use in implementing embodiments of the present disclosure is shown. The terminal device in the embodiments of the present disclosure may include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a vehicle terminal (e.g., a car navigation terminal), and the like, and a stationary terminal such as a digital TV, a desktop computer, and the like. The electronic device shown in fig. 9 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 9, electronic device 600 may include a processing means (e.g., central processing unit, graphics processor, etc.) 601 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage means 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the electronic apparatus 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
Generally, the following devices may be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 607 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 608 including, for example, tape, hard disk, etc.; and a communication device 609. The communication means 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. While fig. 9 illustrates an electronic device 600 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer readable medium, the computer program containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means 609, or may be installed from the storage means 608, or may be installed from the ROM 602. The computer program, when executed by the processing device 601, performs the above-described functions defined in the methods of the embodiments of the present disclosure.
It should be noted that the computer readable medium in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.
The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring a target image, wherein the target image comprises a target object and object description information of the target object; extracting a key information feature sequence of the target object and a multi-modal feature sequence corresponding to a target attribute of the target object from the target image, wherein the multi-modal feature sequence comprises a visual feature sequence and a semantic feature sequence of the target attribute; determining a plurality of object attributes of the target object according to the key information feature sequence and the multi-modal feature sequence, wherein the plurality of object attributes include the target attribute.
Computer program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including but not limited to an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present disclosure may be implemented by software or hardware. The name of the module does not in some cases constitute a limitation of the module itself, and for example, the acquisition module may also be described as a "module that acquires a target image".
The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
In accordance with one or more embodiments of the present disclosure, example 1 provides an object attribute identification method, including: acquiring a target image, wherein the target image comprises a target object and object description information of the target object; extracting a key information feature sequence of the target object and a multi-modal feature sequence corresponding to a target attribute of the target object from the target image, wherein the multi-modal feature sequence comprises a visual feature sequence and a semantic feature sequence of the target attribute; determining a plurality of object attributes of the target object according to the key information feature sequence and the multi-modal feature sequence, wherein the plurality of object attributes include the target attribute.
Example 2 provides the method of example 1, the extracting, from the target image, a multimodal feature sequence corresponding to a target attribute of the target object, including:
and inputting the target image into a pre-trained multi-modal feature extraction model to obtain a multi-modal feature sequence corresponding to the target attribute of the target object.
Example 3 provides the method of example 2, the multi-modal feature extraction model comprising: the first target detection module is used for extracting a first area where the identification of the target attribute of the target object is located from the target image; the first preprocessing module is connected with the first target detection module and used for normalizing the first area into an image with a first preset size and straightening the image obtained after normalization into a one-dimensional row vector with a first preset length; the first full-connection module is connected with the first preprocessing module and used for generating a visual feature sequence of the target attribute according to the one-dimensional row vector with the first preset length; the text recognition module is connected with the first target detection module and used for performing text recognition on the first area to obtain an attribute description text of the target attribute; the multilingual language submodel is connected with the text recognition module and used for extracting a semantic feature sequence of the target attribute from the attribute description text; the splicing module is respectively connected with the first full-connection module and the multilingual language submodel and is used for splicing the visual characteristic sequence of the target attribute and the semantic characteristic sequence to obtain a spliced sequence; the first coding module is connected with the splicing module and used for coding the splicing sequence to obtain a first coding sequence; and the second full-connection module is connected with the first coding module and is used for performing dimensionality reduction processing on the first coding sequence to obtain a multi-modal characteristic sequence with preset dimensionality corresponding to the target attribute.
Example 4 provides the method of example 1, the extracting a key information feature sequence of the target object from the target image, including: performing text recognition on the target image to obtain a recognition text, wherein the recognition text is a multilingual text or a monolingual text; and inputting the recognition text into a pre-trained multilingual language model to obtain a key information characteristic sequence of the target object.
Example 5 provides the method of example 1, wherein determining a plurality of object properties of the target object from the key information feature sequence and the multi-modal feature sequence, according to one or more embodiments of the present disclosure, includes: inputting the key information characteristic sequence and the multi-modal characteristic sequence into a pre-trained multi-modal fusion model to obtain a plurality of object attributes of the target object; wherein the multimodal fusion model comprises: the second coding module is used for coding a first feature matrix formed by the key information feature sequence and the multi-modal feature sequence to obtain a second coding sequence, wherein the dimensionalities of the key information feature sequence and the multi-modal feature sequence are preset dimensionalities; and the first decoding modules are respectively connected with the second coding module and used for generating the object attributes under the corresponding attribute categories according to the second coding sequence, wherein the attribute categories of the object attributes are different.
Example 6 provides the method of any one of examples 1-5, further comprising, in accordance with one or more embodiments of the present disclosure: extracting an appearance characteristic sequence of the target object from the target image; the determining a plurality of object attributes of the target object according to the key information feature sequence and the multi-modal feature sequence includes: and determining a plurality of object attributes of the target object according to the key information characteristic sequence, the multi-modal characteristic sequence and the appearance characteristic sequence.
Example 7 provides the method of example 6, the extracting of the sequence of appearance features of the target object from the target image, according to one or more embodiments of the present disclosure, including: inputting the target image into a pre-trained appearance feature extraction model to obtain an appearance feature sequence of the target object, wherein the appearance feature extraction model comprises a second target detection module, a second preprocessing module, a third coding module and a third full-connection module which are connected in sequence; the second target detection module is used for extracting a second area where the appearance of the target object is located from the target image; the second preprocessing module is used for normalizing the second area into an image with a second preset size and straightening the image obtained after normalization into a one-dimensional row vector with a second preset length; the third coding module is configured to code the one-dimensional row vector with the second preset length to obtain a third coding sequence; and the third full-connection module is used for performing dimensionality reduction processing on the third coding sequence to obtain an appearance characteristic sequence of the target object with preset dimensionality.
Example 8 provides the method of example 6, further comprising, in accordance with one or more embodiments of the present disclosure: extracting a global visual feature sequence of the target image from the target image; the determining a plurality of object attributes of the target object according to the key information feature sequence, the multi-modal feature sequence, and the appearance feature sequence includes: determining a plurality of object attributes of the target object according to the key information feature sequence, the multi-modal feature sequence, the appearance feature sequence and the global visual feature sequence.
Example 9 provides the method of example 8, the extracting a global visual feature sequence of the target object from the target image, according to one or more embodiments of the present disclosure, including: inputting the target image into a pre-trained global visual feature extraction model to obtain a global visual feature sequence of the target image, wherein the global visual feature extraction model comprises a third preprocessing module, a fourth fully-connected module, a fourth coding module and a second decoding module which are connected in sequence; the third preprocessing module is configured to adjust the target image to a third preset size, divide the target image obtained after size adjustment into a plurality of image blocks according to a fourth preset size, straighten each image block into one-dimensional eigenvectors of a third preset length, and form one-dimensional eigenvectors of the third preset length into a second feature matrix; the fourth full-connection module is configured to generate an original feature sequence corresponding to the target image according to the second feature matrix; the fourth coding module is used for coding the original characteristic sequence to obtain a fourth coding sequence; and the second decoding module is used for decoding the fourth coding sequence to obtain a global visual feature sequence of the target image.
Example 10 provides, in accordance with one or more embodiments of the present disclosure, an object property identification apparatus, comprising: the device comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring a target image, and the target image comprises a target object and object description information of the target object; the first extraction module is used for extracting a key information feature sequence of the target object and a multi-modal feature sequence corresponding to a target attribute of the target object from the target image acquired by the acquisition module, wherein the multi-modal feature sequence comprises a visual feature sequence and a semantic feature sequence of the target attribute; a determining module, configured to determine a plurality of object attributes of the target object according to the key information feature sequence and the multi-modal feature sequence extracted by the first extracting module, where the plurality of object attributes include the target attribute.
Example 11 provides a computer-readable medium having stored thereon a computer program that, when executed by a processing apparatus, performs the steps of the method of any of examples 1-9, in accordance with one or more embodiments of the present disclosure.
Example 12 provides, in accordance with one or more embodiments of the present disclosure, an electronic device, comprising: a storage device having a computer program stored thereon; processing means for executing the computer program in the storage means to carry out the steps of the method of any of examples 1-9.
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure herein is not limited to the particular combination of features described above, but also encompasses other embodiments in which any combination of the features described above or their equivalents does not depart from the spirit of the disclosure. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.
Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination.
Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims. With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Claims (12)
1. An object attribute identification method, comprising:
acquiring a target image, wherein the target image comprises a target object and object description information of the target object;
extracting a key information feature sequence of the target object and a multi-modal feature sequence corresponding to a target attribute of the target object from the target image, wherein the multi-modal feature sequence comprises a visual feature sequence and a semantic feature sequence of the target attribute;
determining a plurality of object attributes of the target object according to the key information feature sequence and the multi-modal feature sequence, wherein the plurality of object attributes include the target attribute.
2. The method according to claim 1, wherein the extracting a multi-modal feature sequence corresponding to the target attribute of the target object from the target image comprises:
and inputting the target image into a pre-trained multi-modal feature extraction model to obtain a multi-modal feature sequence corresponding to the target attribute of the target object.
3. The method of claim 2, wherein the multi-modal feature extraction model comprises:
the first target detection module is used for extracting a first area where the identification of the target attribute of the target object is located from the target image;
the first preprocessing module is connected with the first target detection module and used for normalizing the first area into an image with a first preset size and straightening the image obtained after normalization into a one-dimensional row vector with a first preset length;
the first full-connection module is connected with the first preprocessing module and used for generating a visual feature sequence of the target attribute according to the one-dimensional row vector with the first preset length;
the text recognition module is connected with the first target detection module and used for performing text recognition on the first area to obtain an attribute description text of the target attribute;
the multilingual language submodel is connected with the text recognition module and used for extracting a semantic feature sequence of the target attribute from the attribute description text;
the splicing module is respectively connected with the first full-connection module and the multilingual language submodel and is used for splicing the visual characteristic sequence of the target attribute and the semantic characteristic sequence to obtain a spliced sequence;
the first coding module is connected with the splicing module and used for coding the splicing sequence to obtain a first coding sequence;
and the second full-connection module is connected with the first coding module and is used for performing dimensionality reduction processing on the first coding sequence to obtain a multi-modal characteristic sequence with preset dimensionality corresponding to the target attribute.
4. The method according to claim 1, wherein the extracting the key information feature sequence of the target object from the target image comprises:
performing text recognition on the target image to obtain a recognition text, wherein the recognition text is a multilingual text or a monolingual text;
and inputting the recognition text into a pre-trained multilingual language model to obtain a key information characteristic sequence of the target object.
5. The method according to claim 1, wherein the determining a plurality of object properties of the target object from the key information feature sequence and the multi-modal feature sequence comprises:
inputting the key information characteristic sequence and the multi-modal characteristic sequence into a pre-trained multi-modal fusion model to obtain a plurality of object attributes of the target object;
wherein the multimodal fusion model comprises:
the second coding module is used for coding a first feature matrix formed by the key information feature sequence and the multi-modal feature sequence to obtain a second coding sequence, wherein the dimensionalities of the key information feature sequence and the multi-modal feature sequence are preset dimensionalities;
and the first decoding modules are respectively connected with the second coding module and used for generating the object attributes under the corresponding attribute categories according to the second coding sequence, wherein the attribute categories of the object attributes are different.
6. The method according to any one of claims 1-5, further comprising:
extracting an appearance characteristic sequence of the target object from the target image;
the determining a plurality of object attributes of the target object according to the key information feature sequence and the multi-modal feature sequence includes:
and determining a plurality of object attributes of the target object according to the key information characteristic sequence, the multi-modal characteristic sequence and the appearance characteristic sequence.
7. The method of claim 6, wherein the extracting the appearance feature sequence of the target object from the target image comprises:
inputting the target image into a pre-trained appearance feature extraction model to obtain an appearance feature sequence of the target object, wherein the appearance feature extraction model comprises a second target detection module, a second preprocessing module, a third coding module and a third full-connection module which are connected in sequence;
the second target detection module is used for extracting a second area where the appearance of the target object is located from the target image;
the second preprocessing module is used for normalizing the second area into an image with a second preset size and straightening the image obtained after normalization into a one-dimensional row vector with a second preset length;
the third coding module is configured to code the one-dimensional row vector with the second preset length to obtain a third coding sequence;
and the third full-connection module is used for performing dimensionality reduction processing on the third coding sequence to obtain an appearance characteristic sequence of the target object with preset dimensionality.
8. The method of claim 6, further comprising:
extracting a global visual feature sequence of the target image from the target image;
the determining a plurality of object attributes of the target object according to the key information feature sequence, the multi-modal feature sequence, and the appearance feature sequence includes:
determining a plurality of object attributes of the target object according to the key information feature sequence, the multi-modal feature sequence, the appearance feature sequence and the global visual feature sequence.
9. The method of claim 8, wherein the extracting the global visual feature sequence of the target object from the target image comprises:
inputting the target image into a pre-trained global visual feature extraction model to obtain a global visual feature sequence of the target image, wherein the global visual feature extraction model comprises a third preprocessing module, a fourth fully-connected module, a fourth coding module and a second decoding module which are connected in sequence;
the third preprocessing module is configured to adjust the target image to a third preset size, divide the target image obtained after the size adjustment into a plurality of image blocks according to a fourth preset size, straighten each image block into one-dimensional eigenvectors of a third preset length, and form a second eigenvector of the third preset length into a second eigenvector matrix;
the fourth full-connection module is configured to generate an original feature sequence corresponding to the target image according to the second feature matrix;
the fourth coding module is used for coding the original characteristic sequence to obtain a fourth coding sequence;
and the second decoding module is used for decoding the fourth coding sequence to obtain a global visual feature sequence of the target image.
10. An object attribute identification apparatus, comprising:
the device comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for acquiring a target image, and the target image comprises a target object and object description information of the target object;
the first extraction module is used for extracting a key information feature sequence of the target object and a multi-modal feature sequence corresponding to a target attribute of the target object from the target image acquired by the acquisition module, wherein the multi-modal feature sequence comprises a visual feature sequence and a semantic feature sequence of the target attribute;
a determining module, configured to determine a plurality of object attributes of the target object according to the key information feature sequence and the multi-modal feature sequence extracted by the first extracting module, where the plurality of object attributes include the target attribute.
11. A computer-readable medium, on which a computer program is stored which, when being executed by a processing means, carries out the steps of the method according to any one of claims 1-9.
12. An electronic device, comprising:
a storage device having a computer program stored thereon;
processing means for executing the computer program in the storage means to carry out the steps of the method according to any one of claims 1 to 9.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210074401.6A CN114429552A (en) | 2022-01-21 | 2022-01-21 | Object attribute identification method and device, readable storage medium and electronic equipment |
| PCT/CN2022/141994 WO2023138314A1 (en) | 2022-01-21 | 2022-12-26 | Object attribute recognition method and apparatus, readable storage medium, and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210074401.6A CN114429552A (en) | 2022-01-21 | 2022-01-21 | Object attribute identification method and device, readable storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114429552A true CN114429552A (en) | 2022-05-03 |
Family
ID=81313847
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210074401.6A Pending CN114429552A (en) | 2022-01-21 | 2022-01-21 | Object attribute identification method and device, readable storage medium and electronic equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN114429552A (en) |
| WO (1) | WO2023138314A1 (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023138314A1 (en) * | 2022-01-21 | 2023-07-27 | 北京有竹居网络技术有限公司 | Object attribute recognition method and apparatus, readable storage medium, and electronic device |
| CN117274953A (en) * | 2023-09-28 | 2023-12-22 | 深圳市厚朴科技开发有限公司 | Vehicle and pedestrian attribute identification method system, device and medium |
| WO2023246641A1 (en) * | 2022-06-24 | 2023-12-28 | 华为云计算技术有限公司 | Method and apparatus for identifying object, and storage medium |
| CN117351205A (en) * | 2023-10-23 | 2024-01-05 | 中国人民解放军陆军工程大学 | Image structured information extraction method |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111428593A (en) * | 2020-03-12 | 2020-07-17 | 北京三快在线科技有限公司 | Character recognition method and device, electronic equipment and storage medium |
| CN111461203A (en) * | 2020-03-30 | 2020-07-28 | 北京百度网讯科技有限公司 | Cross-modal processing method and device, electronic equipment and computer storage medium |
| CN112001248B (en) * | 2020-07-20 | 2024-03-01 | 北京百度网讯科技有限公司 | Active interaction method, device, electronic equipment and readable storage medium |
| CN114429552A (en) * | 2022-01-21 | 2022-05-03 | 北京有竹居网络技术有限公司 | Object attribute identification method and device, readable storage medium and electronic equipment |
-
2022
- 2022-01-21 CN CN202210074401.6A patent/CN114429552A/en active Pending
- 2022-12-26 WO PCT/CN2022/141994 patent/WO2023138314A1/en unknown
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023138314A1 (en) * | 2022-01-21 | 2023-07-27 | 北京有竹居网络技术有限公司 | Object attribute recognition method and apparatus, readable storage medium, and electronic device |
| WO2023246641A1 (en) * | 2022-06-24 | 2023-12-28 | 华为云计算技术有限公司 | Method and apparatus for identifying object, and storage medium |
| CN117274953A (en) * | 2023-09-28 | 2023-12-22 | 深圳市厚朴科技开发有限公司 | Vehicle and pedestrian attribute identification method system, device and medium |
| CN117351205A (en) * | 2023-10-23 | 2024-01-05 | 中国人民解放军陆军工程大学 | Image structured information extraction method |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023138314A1 (en) | 2023-07-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114429552A (en) | Object attribute identification method and device, readable storage medium and electronic equipment | |
| CN110826567B (en) | Optical character recognition method, device, equipment and storage medium | |
| CN112766284B (en) | Image recognition method and device, storage medium and electronic equipment | |
| CN112270200B (en) | Text information translation method and device, electronic equipment and storage medium | |
| CN113449070A (en) | Multimodal data retrieval method, device, medium and electronic equipment | |
| US20240078385A1 (en) | Method and apparatus for generating text | |
| CN113377914A (en) | Recommended text generation method and device, electronic equipment and computer readable medium | |
| CN113254684A (en) | Content aging determination method, related device, equipment and storage medium | |
| CN115578570A (en) | Image processing method, device, readable medium and electronic equipment | |
| CN113591490B (en) | Information processing method and device and electronic equipment | |
| CN114463769A (en) | Form recognition method and device, readable medium and electronic equipment | |
| CN114067327A (en) | Text recognition method and device, readable medium and electronic equipment | |
| CN111898338A (en) | Text generation method and device and electronic equipment | |
| CN114970470B (en) | Method and device for processing file information, electronic equipment and computer readable medium | |
| CN115984868A (en) | Text processing method, device, medium and equipment | |
| CN113986958B (en) | Text information conversion method and device, readable medium and electronic equipment | |
| CN114943583A (en) | User favorite article information generation method and device, electronic equipment and medium | |
| CN114511744A (en) | Image classification method and device, readable medium and electronic equipment | |
| CN114429629A (en) | Image processing method and device, readable storage medium and electronic equipment | |
| CN114495081A (en) | Text recognition method and device, readable medium and electronic equipment | |
| CN113191257A (en) | Order of strokes detection method and device and electronic equipment | |
| CN112765377A (en) | Time slot positioning in media streams | |
| CN115098647B (en) | Feature vector generation method and device for text representation and electronic equipment | |
| CN116974684B (en) | Map page layout method, map page layout device, electronic equipment and computer readable medium | |
| CN114625876B (en) | Method for generating author characteristic model, method and device for processing author information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |